To evaluate the image quality, interpretation consistency, and scanning efficiency of deep learning-based reconstruction (DLR) algorithm (AIR™ Recon DL; GE Healthcare) compared with conventional reconstruction (ConR) in T2-weighted MRI for rectal cancer across different number of excitations (NEX) values. This prospective study enrolled consecutive patients undergoing MRI for primary staging of rectal cancer between July 2022 and April 2023. Each patient underwent T2-weighted MRI with three NEX values (4, 2, and 1), reconstructed using both ConR and DLR methods, generating six image sets. Image quality was assessed quantitatively (signal-to-noise ratio, contrast-to-noise ratio) and qualitatively using a 5-point scale for tissue contrast, edge sharpness, rectal wall morphology, tumor characteristics, overall image quality, and noise. Two radiologists independently evaluated staging parameters including T stage, N stage, extramural vascular invasion (EMVI), and mesorectal fascia (MRF) status. Inter-observer and inter-sequence agreement were analyzed. Thirty-five patients completed all six imaging protocols. Acquisition times were 3 min 55s (NEX = 4), 2 min 1s (NEX = 2, 49

Clinicians need a reliable, noninvasive tool that can predict the risk of gastrointestinal stromal tumor (GIST) recurrence preoperatively. We aimed to develop a machine learning model based on preoperative contrast-enhanced CT (CECT) to predict recurrence-free survival (RFS) in GIST patients who underwent radical resection. A total of 192 patients with intermediate- and high-risk GISTs who underwent radical resection and subsequently received adjuvant imatinib were included, with a minimum follow-up duration of 24 months. A deep learning model (Modelradiomic) based on preoperative CECT was built to predict RFS, which was compared with the Armed Forces Institute of Pathology (AFIP) index (ModelAFIP). The C-index and time-dependent receiver operating characteristic curves were estimated via the Kaplan-Meier method and compared via the log-rank test. The C-index values of the Modelradiomic in the training, testing and validation cohorts ranged from 0.678 to 0.763, whereas the areas under the curves (AUCs) at 3 and 5 years were 0.744–0.790 and 0.703–0.833, respectively. The C-index values of ModelAFIP in the above datasets were 0.539–0.660, and the AUCs at 3 and 5 years were 0.497–0.649 and 0.503–0.630. Modelradiomic demonstrated a higher C-index than ModelAFIP did in the training and external validation cohorts (p = 0.010 and 0.042, respectively). Modelradiomic presented a greater AUC value than ModelAFIP did at the 5th year in the training cohort (p = 0.009). We found the machine learning-based preoperative CECT performed better than the AFIP index in prediction of RFS of GIST patients, especially at the 5th year, predicting recurrence risk in patients who underwent radical resection and receiving adjuvant therapy. This model may serve as a non-invasive tool to identify high-risk individuals who require more intensive surveillance and personalized management following radical resection.

Magnetic resonance imaging (MRI) has high soft-tissue resolution; thus, it is an important imaging modality for evaluating treatment responses. However, treatment-induced fibrosis, inflammation, and mucin pool formation lead to a cross between imaging and pathological phenotypes, which considerably increases the uncertainty of interpretation. This paper systematically reviews the research progress of comparative studies on MRI assessment and postoperative pathology after neoadjuvant therapy for rectal cancer and its significance in predicting surgical prognosis. This paper proposes a standardized framework for MRI assessment of rectal cancer, emphasizing the stable extraction of key risk indicators through the integrated interpretation of multisequence images based on unified scanning protocols and structured reporting. This study focused on parameters directly related to surgical decision-making, such as primary tumor bed staging, lymph node status, risk of circumferential resection margin involvement, and extramural venous invasion and evaluated the consistency between their imaging manifestations and pathological results, as well as the clinical translational value. The results showed that imaging-pathological inconsistency was jointly affected by factors such as histological heterogeneity, upper limit of spatial resolution, differences in diagnosis and treatment processes, and time-dependent tumor regression. Clinical practice should combine multimodal information and dynamic assessment to transform imaging findings into an actionable basis for risk stratification to improve the accuracy of individualized treatment decisions and enhance the clinical usability of imaging indicators.

3535 Background: Multiple large-scale prospective studies have confirmed that neoadjuvant chemotherapy (NCT) alone can achieve optimal distant and local control in locally advanced rectal cancers (LARC) without high risks. However, due to the potentially lower overall response rate compared to chemo-radiotherapy, it is rational to discontinue ineffective NCT in chemo-resistant patients. In our phase II study, we applied 4 cycles of Capox in LARC patients with low to intermediate risks, observing a considerable patho-clinical response rate and an accuracy of 0.89 in predicting non-responders using MRI features after two cycles of Capox. To determine the optimal number of NCT cycles and prevent unnecessary prolonged treatment, we conducted this phase III trial to assess the non-inferiority of two cycles of NCT compared to four cycles with respect to the final pathological tumor response grade (pTRG) of 3. Methods: This multicenter, non-inferiority, phase III randomized controlled trial was conducted at 14 centers across China. Eligible patients with low- to intermediate-risk stage II/III rectal cancer were randomized to receive either 2 or 4 cycles of CAPOX, followed by total mesorectal excision (TME) surgery. The primary endpoint was the proportion of patients with a poor pathological response to NCT (pTRG 3). Secondary outcomes included the accuracy of MRI in predicting tumor response, treatment-related adverse events, and 3-year survival outcomes. Results: From August 6, 2021, to May 27, 2024, a total of 573 patients were enrolled. Ultimately, 527 patients (2-cycle group, 266 vs. 4-cycle group, 261) were included in the primary analysis. The pTRG 3 rate in the 2-cycle group (27.8%, 74/266) was non-inferior to that in the 4-cycle group (26.4%, 69/261, p = 0.722). Better lymph node response was observed in the 4-cycle group (pN negative: 83.1%, 217/261 vs. 72.5%, 193/266, p = 0.011). The incidence of major adverse events (grade ≥3, according to CTCAE 5.0) was comparable between the two groups (37.9% vs. 44.8%, p = 0.094). A tumor longitudinal length reduction rate (TLLR) of less than 30% on MRI predicted pathological poor responders with a high positive predictive value of 0.918 after two cycles of NCT in the two-cycle group, 0.864 after two cycles of NCT in the four-cycle group, and 0.841 after four cycles of NCT in the four-cycle group. Conclusions: Four cycles of NCT do not result in a greater reduction in poor pathological response compared to two cycles, highlighting the importance of early response assessment. MRI evaluation of tumor response after 2 cycles predict the final pathological results with considerable accuracy. These findings lay the groundwork for future studies exploring response-guided treatment approaches in rectal cancer. Clinical trial information: NCT04922853 .

Congenital extrahepatic portosystemic shunt, also known as Abernethy malformation, is a rare anatomic vascular malformation. Patients with Abernethy malformation may present with abdominal pain, abnormal liver function tests, hepatopulmonary syndrome, pulmonary hypertension, and/or portosystemic encephalopathy. Accurate identification of the shunt and portal vein and effective management of complications is vital in these patients. Routine imaging examinations are useful for the diagnosis and classification of Abernethy malformation. However, these examinations may miss some portal vein branches. Digital subtraction angiography is invaluable when routine imaging cannot precisely identify the hepatic portal vein in this situation.

Flexible radio frequency (RF) coils can conform to the contours of the human body, enhancing image quality for magnetic resonance imaging (MRI). A universal flexible coil is essential for a wide range of applications. In this study, a 24-channel flexible coil (FC24) was designed and constructed for MRI in multiple applications, particularly for imaging the head, knee and abdomen. In the human studies, the signal-to-noise ratio (SNR) improvement of the FC24 was about 20% and 19% in the transversal and coronal planes, respectively, when compared to that of a 24-channel head and neck coil (HNC24). Compared to a 24-channel knee coil (KC24), the FC24 has SNR improvement about 13% in the transversal plane, 35% in the sagittal plane and 22% in the coronal plane. The FC24 demonstrated not only higher SNR and considerable parallel imaging performance, but also improved image quality when compared to the HNC24 and the KC24 in T1-weighted and T2-weighted fast spin echo imaging. Additionally, the FC24 achieved the same image quality as the 24-channel abdomen coil. Overall, the FC24 has shown excellent performance and versatility in imaging various anatomical regions, indicating its great potential for clinical applications.

Accurate preoperative MRI classification of gliomas is essential but challenging due to complex radiological features and inter-observer variability. This study evaluated three large language models (LLMs) for VASARI-based glioma classification compared to radiologist interpretations. We retrospectively analyzed 150 histopathologically confirmed gliomas (43 circumscribed astrocytic, 53 high-grade diffuse, 54 low-grade diffuse gliomas) using standardized MRI protocols. Three radiologists extracted VASARI features, while three LLMs (GPT-4, Claude3.5-Sonnet, Claude3.0-Opus) analyzed these features using standard input-output or knowledge-enhanced prompting incorporating diagnostic guidelines. Knowledge-enhanced prompting consistently outperformed standard prompting, improving diagnostic consistency (intra-model agreement: Sonnet κ = 0.91, Opus κ = 0.92, GPT-4 κ = 0.72). For diffuse versus circumscribed classification, senior radiologists (AUC = 0.88) and Claude3.5-Sonnet with knowledge-enhanced prompting (AUC = 0.84) performed similarly (p > 0.05). LLM assistance significantly improved junior radiologists’ performance, with AUC increases from 0.77 to 0.83 (p = 0.026). Knowledge-enhanced LLMs demonstrate diagnostic performance comparable to experienced radiologists and improve junior accuracy, suggesting potential as decision-support tools requiring radiologist oversight.

Wireless radiofrequency (RF) coils based on metasurfaces hold great promise for improving clinical magnetic resonance imaging (MRI) workflows by eliminating the need for cable connections to the patient bed and simplifying coil structures. A fundamental requirement for their clinical adoption is the ability to support parallel imaging, which reduces examination time and improves efficiency. Moreover, the implementation of parallel imaging often comes at the expense of image signal-to-noise ratio (SNR). Although several wireless RF coils incorporating metamaterials are reported, most do not support parallel imaging and many deliver suboptimal SNR performance. In this work, a novel wireless RF coil architecture is proposed, termed the near-field coupling array (NFCA), which demonstrates both excellent SNR performance and robust parallel imaging capabilities. A general theoretical framework is presented that establishes a foundation for applying metasurface arrays in magnetic resonance RF coil design. The SNR expression for this architecture is derived from two perspectives, and its fundamental principles are validated through case studies. Experimental results show that the NFCA achieves a 66% SNR improvement over a conventional commercial RF coil architecture (i.e., a wired coil) while its average acceleration factor exceeds 94% of that of the commercial coil.

Delayed diagnosis of inflammatory bowel disease (IBD) is common, there is still no effective imaging system to distinguish Crohn's Disease (CD) and Ulcerative Colitis (UC) patients. This multicenter retrospective study included IBD patients at three centers between January 2012 and May 2022. The intestinal and perianal imaging signs were evaluated. Visceral fat information from CT images was extracted, including the ratio of visceral to subcutaneous fat volume (VSR), fat distribution, and attenuation values. The valuable indicators were screened out in the derivation cohort by binary logistic regression and receiver working curve (ROC) analysis to construct an imaging report and data system for IBD (IBD-RADS), which was tested in the validation cohort. The derivation cohort included 606 patients (365 CD, 241 UC), and the validation cohort included 155 patients (97 CD, 58 UC). Asymmetric enhancement (AE) (OR = 87.75 [28.69, 268.4]; P < 0.001), perianal fistula (OR = 4.968 [1.807, 13.66]; P = 0.002) and VSR (OR = 1.571 [1.087, 2.280]; P = 0.04) were independent predictors of CD. VSR improved the efficiency of imaging signs (AUC: 0.929 vs. 0.901; P < 0.001), with a threshold greater than 0.97 defined as visceral fat predominance (VFP). In IBD-RADS, AE was the major criterion, VFP and perianal fistula were auxiliary criteria, and intestinal fistula, limited small bowel disease, and skip distribution were special favoring items as their 100

The performance of radiofrequency (RF) coils has a significant impact on the quality and speed of magnetic resonance imaging (MRI). Consequently, rigid coils with attached cables are commonly employed to achieve optimal SNR performance and parallel imaging capability. However, since the adoption of MRI in clinical imaging, both patients and doctors have long suffered from the poor examination experience and physical strain caused by the bulky housings and cumbersome cables of traditional coils. This paper presents a new architectural concept, the Near-Field Coupling (NFC) coil system, which integrates a pickup coil array within the magnet with an NFC coil worn by the patient. In contrast to conventional coils, the NFC coil system obviates the necessity for bed-mounted connectors. It provides a lightweight, cost-effective solution that enhances patient comfort and supports disposable, custom designs for the NFC coils. The paper also derives the SNR expression for the NFC coil system, proposes two key design principles, and demonstrates the system's potential in SNR and parallel imaging through an implementation case.

This study investigates the cardioprotective effects of Paeoniflorin (PF) on left ventricular remodeling following acute myocardial infarction (AMI) under conditions of hypobaric hypoxia. Left ventricular remodeling post-AMI plays a pivotal role in exacerbating heart failure, especially at high altitudes. Using a rat model of AMI, the study aimed to evaluate the cardioprotective potential of PF under hypobaric hypoxia. Ninety male rats were divided into four groups: sham-operated controls under normoxia/hypobaria, an AMI model group, and a PF treatment group. PF was administered for 4 weeks after AMI induction. Left ventricular function was assessed using cardiac magnetic resonance imaging. Biochemical assays of cuproptosis, oxidative stress, apoptosis, inflammation, and fibrosis were performed. Results demonstrated PF significantly improved left ventricular function and remodeling after AMI under hypobaric hypoxia. Mechanistically, PF decreased FDX1/DLAT expression and serum copper while increasing pyruvate. It also attenuated apoptosis, inflammation, and fibrosis by modulating Bcl-2, Bax, NLRP3, and oxidative stress markers. Thus, PF exhibits therapeutic potential for left ventricular remodeling post-AMI at high altitude by inhibiting cuproptosis, inflammation, apoptosis and fibrosis. Further studies are warranted to optimize dosage and duration and elucidate PF’s mechanisms of action.

Abstract Objectives To achieve automated quantification of visceral adipose tissue (VAT) distribution in CT images and screen out parameters with discriminative value for inflammatory bowel disease (IBD) subtypes. Methods This retrospective multicenter study included Crohn’s disease (CD) and ulcerative colitis (UC) patients from three institutions between 2012 and 2021, with patients with acute appendicitis as controls. An automatic VAT segmentation algorithm was developed using abdominal CT scans. The VAT volume, as well as the coefficient of variation (CV) of areas within the lumbar region, was calculated. Binary logistic regression and receiver operating characteristic analysis was performed to evaluate the potential of indicators to distinguish between IBD subtypes. Results The study included 772 patients (365 CDs, median age [inter-quartile range] = 31.0. (25.0, 42.0) years, 255 males; 241 UCs, 46.0 (34.0, 55.5) years, 138 males; 166 controls, 40.0 (29.0, 53.0) years, 80 males). CD patients had lower VAT volume (CD = 1584.95 ± 1128.31 cm3, UC = 1855.30 ± 1326.12 cm3, controls = 2470.91 ± 1646.42 cm3) but a higher CV (CD = 29.42 ± 15.54 %, p = 0.006 and p ˂ 0.001) compared to UC and controls (25.69 ± 12.61 % vs. 23.42 ± 15.62 %, p = 0.11). Multivariate analysis showed CV was a significant predictor for CD (odds ratio = 6.05 (1.17, 31.12), p = 0.03). The inclusion of CV improved diagnostic efficiency (AUC = 0.811 (0.774, 0.844) vs. 0.803 (0.766, 0.836), p = 0.08). Conclusion CT-based VAT distribution can serve as a potential biomarker for distinguishing IBD subtypes. Critical relevance statement Visceral fat distribution features extracted from CT images using an automated segmentation algorithm (1.14 min) show differences between Crohn’s disease and ulcerative colitis and are promising for practical radiological screening. Key points • Radiological parameters reflecting visceral fat distribution were extracted for the discrimination of Crohn’s disease (CD) and ulcerative colitis (UC). • In CD, visceral fat was concentrated in the lower lumbar vertebrae, and the coefficient of variation was a significant predictor (OR = 6.05 (1.17, 31.12), p = 0.03). • The differences between CD, UC, and controls are promising for practical radiological screening. Graphical Abstract

LBA3511 Background: Distant metastases remain a common problem in locally advanced rectal cancer (LARC) patients who received neoadjuvant chemoradiotherapy (NCRT) and surgery. Previous researchers have demonstrated the survival benefits of total neoadjuvant treatment (TNT) using short-course radiotherapy with CAPOX and long-course radiotherapy (LCRT) with mFOLFIRINOX. This study aimed to explore the efficacy of TNT using long-course radiotherapy (LCRT) combined with CAPOX. Methods: In this phase 3, open-label, multicenter, randomized trial, eligible pts were diagnosed as stage II/III and had at least one high risk factor: cT4a-b (resectable), cT3c-d with extramural venous invasion, cN2; involved mesorectal fascia, or enlarged lateral lymph nodes. Pts were randomly assigned to either Arm A to receive TNT (LCRT with six cycles of neoadjuvant CAPOX (one cycle of induction CAPOX, two cycles of concurrent CAPOX, and three cycles of consolidation CAPOX) followed by total mesorectal excision (TME)) or Arm B to receive NCRT (LCRT with concomitant capecitabine, followed by TME and adjuvant CAPOX). Radiotherapy in both groups was administered at 50-50.4 Gy in 25-28 fractions. The primary endpoint was disease free survival (DFS). The secondary endpoints were pathological response complete (pCR) rate, overall survival (OS), metastasis-free survival (MFS) and postoperative 30-day morbidity. Results: (ITT) Between June 6, 2017, and Mar 5, 2024, 458 pts were randomly assigned to two Arms (232 in Arm A, and 226 in Arm B). At a median follow-up of 44 months (IQR, 24-57.25), the 3-yr DFS was significantly increased in Arm A (77.0% vs 67.9% in Arm A/B respectively, HR 0.623, 95% CI 0.435-0.892, p = 0.009). 3-yr MFS was also significantly higher in arm A: 83.0% vs 74.2% in arm B (HR 0.595, 95% CI 0.392-0.903, p= 0.013). A total of 56 OS events was reported, and the 3-yr OS was 90.3% vs 87.9% (HR 0.747, 95% CI 0.441-1.266, p = 0.276) in arm A/B, respectively. TNT and NCRT in both arms were well tolerated. Thrombocytopenia was the most frequent grade 3-4 hematological adverse event in Arm A, occurring in 24 (10.3%) of 232 pts. Until now, 27.5% of pts achieved pCR in Arm A, compared to only 9.9% in Arm B. (OR 3.436, [1.1.941-6.084], p= 0.0001). In Arm A and B, 13 and 2 pts achieved clinical complete response (cCR) and received watch-and-wait strategy, respectively. No significant difference in severe morbidity within 30 days post-operation were found between the two arms. Conclusions: TNT with LCRT combined with CAPOX significantly improve DFS, MFS and pCR compared to standard concurrent neoadjuvant chemoradiotherapy in LARC patients with high risk factors, with acceptable toxicities. Clinical trial information: NCT03177382 .

Purpose: To investigate the effectiveness of simultaneous multislice (SMS) accelerated readout-segmented echo planar imaging (RESOLVE) DWI for assessing rectal cancer in the clinic.Method: Sixty consecutive histologically proven rectal cancer patients were enrolled. They all received MRI examinations, including both SMS-RESOLVE and RESOLVE sequences. Two readers visually assessed the overall image quality, distinction of anatomical structures, lesion conspicuity, and artifacts of two sequences by using a qualitative 4-point Likert scale. The quantitative ADC value, lesion contrast, signal-to-noise ratio (SNR), contrast to-noise ratio (CNR) and temporal SNR (tSNR) were independently calculated in rectal cancer on the largest slice of the tumor.Results: The scan time was shortened from 3 min and 50 s to 1 min and 47 s. The interobserver agreement of visual and quantitative assessments between the two readers was good overall. There were no differences in overall image quality, lesion conspicuity or artifact scores between the two sequences in both readers (all p > 0.05). The lesion contrast (p = 0.013) was significantly higher in SMS-RESOLVE, and the CNR was similar in the two DWIs. The scores of distinctions of anatomical structures in SMS-RESOLVE were lower (all p < 0.05) in both readers. The SNR of SMS-RESOLVE was lower than that of RESOLVE (p = 0.004), and the tSNR of SMS-RESOLVE was significantly higher (p < 0.001). The ADC value of the tumor was lower in SMS-RESOLVE (p = 0.001), but the ADC values of the normal rectal wall showed no difference between the two DWIs.Conclusion: SMS-RESOLVE allowed a substantial reduction in acquisition time while maintaining overall image quality and lesion conspicuity in rectal cancer. It also had a higher contrast of the lesion and a higher temporal SNR.

Isotropic dynamic contrast-enhanced magnetic resonance imaging using differential subsampling with cartesian ordering and adaptive imaging receive coil for the diagnosis of Crohn disease: a case description

Ovarian metastasis (OM) from colorectal cancer (CRC) is infrequent and has a poor prognosis. The purpose of this study is to investigate the value of a contrast-enhanced CT-based radiomics model in predicting ovarian metastasis from colorectal cancer outcomes after systemic chemotherapy. A total of 52 ovarian metastatic CRC patients who received first-line systemic chemotherapy were retrospectively included in this study and were categorized into chemo-benefit (C+) and no-chemo-benefit (C−) groups, using Response Criteria in Solid Tumors (RECIST v1.1) as the standard. A total of 1743 radiomics features were extracted from baseline CT, three methods were adopted during the feature selection, and five prediction models were constructed. Receiver operating characteristic (ROC) analysis, calibration analysis, and decision curve analysis (DCA) were used to evaluate the diagnostic performance and clinical utility of each model. Among those machine-learning-based radiomics models, the SVM model showed the best performance on the validation dataset, with AUC, accuracy, sensitivity, and specificity of 0.903 (95% CI, 0.788–0.967), 88.5%, 95.7%, and 82.8%, respectively. All radiomics models exhibited good calibration, and the DCA demonstrated that the SVM model had a higher net benefit than other models across the majority of the range of threshold probabilities. Our findings showed that contrast-enhanced CT-based radiomics models have high discriminating power in predicting the outcome of colorectal cancer ovarian metastases patients receiving chemotherapy.

Although 3D T2W imaging can make up for deficiencies, such as thick layer thickness, low spatial resolution and no retrospective post-processing, of 2D acquisitions, the long imaging time and uncertain diagnostic benefits have limited its clinical application. We compared the quality of 2D, 3D and CS sense accelerated 3D T2W imaging in patients with rectal cancer and found that 3D T2W imaging resembled CS sense accelerated 3D T2W imaging, both superior to 2D acquisitions, while the latter scanning faster than the former. It’s conclude that CS sense accelerated 3D T2W imaging can substitute the 2D acquisitions.

PURPOSE:To develop a model for predicting response to total neoadjuvant treatment (TNT) for patients with locally advanced rectal cancer (LARC) based on baseline magnetic resonance imaging (MRI) and clinical data using artificial intelligence methods. METHODS:Baseline MRI and clinical data were curated from patients with LARC and analyzed using logistic regression (LR) and deep learning (DL) methods to predict TNT response retrospectively. We defined two groups of response to TNT as pathological complete response (pCR) versus non-pCR (Group 1), and high sensitivity [tumor regression grade (TRG) 0 and TRG 1] versus moderate sensitivity (TRG 2 or patients with TRG 3 and a reduction in tumor volume of at least 20% compared to baseline) versus low sensitivity (TRG 3 and a reduction in tumor volume <20% compared to baseline) (Group 2). We extracted and selected clinical and radiomic features on baseline T2WI. Then we built LR models and DL models. Receiver operating characteristic (ROC) curves analysis was performed to assess predictive performance of models. RESULTS:Eighty-nine patients were assigned to the training cohort, and 29 patients were assigned to the testing cohort. The area under receiver operating characteristics curve (AUC) of LR models, which were predictive of high sensitivity and pCR, were 0.853 and 0.866, respectively. Whereas the AUCs of DL models were 0.829 and 0.838, respectively. After 10 rounds of cross validation, the accuracy of the models in Group 1 is higher than in Group 2. CONCLUSION:There was no significant difference between LR model and DL model. Artificial Intelligence-based radiomics biomarkers may have potential clinical implications for adaptive and personalized therapy.

The crack of pipeline girth weld is one of the most common and dangerous defects in girth weld. According to the magnetic dipole theory model, the magnetic signal model of pipeline girth weld cracks is established. By means of numerical simulation, the distribution characteristics of magnetic signals of crack defects in girth welds and the variation rules of magnetic signals of different flaw sizes and lifting heights of girth welds were studied. The simulation results show that the normal component Hy appears zero crossing and changes direction, and the tangential component Hx appears extreme value upward. Finally, the magnetic signal model of crack defects in pipeline girth weld was verified through field engineering test. The actual magnetic induction intensity detected at the flaw of pipeline girth weld was basically consistent with the theoretical calculation results, which verified the accuracy of the model.