Improved Pancreatic Cancer Detection and Localization on CT Scans: A Computer-Aided Detection Model Utilizing Secondary Features.

The early detection of pancreatic ductal adenocarcinoma (PDAC) is essential for optimal treatment of pancreatic cancer patients. We propose a tumor detection framework to improve the detection of pancreatic head tumors on CT scans. In this retrospective research study, CT images of 99 patients with pancreatic head cancer and 98 control cases from the Catharina Hospital Eindhoven were collected. A multi-stage 3D U-Net-based approach was used for PDAC detection including clinically significant secondary features such as pancreatic duct and common bile duct dilation. The developed algorithm was evaluated using a local test set comprising 59 CT scans. The model was externally validated in 28 pancreatic cancer cases of a publicly available medical decathlon dataset. The tumor detection framework achieved a sensitivity of 0.97 and a specificity of 1.00, with an area under the receiver operating curve (AUROC) of 0.99, in detecting pancreatic head cancer in the local test set. In the external test set, we obtained similar results, with a sensitivity of 1.00. The model provided the tumor location with acceptable accuracy obtaining a DICE Similarity Coefficient (DSC) of 0.37. This study shows that a tumor detection framework utilizing CT scans and secondary signs of pancreatic cancer can detect pancreatic tumors with high accuracy.

First-line palliative systemic therapy alternated with oxaliplatin-based pressurized intraperitoneal aerosol chemotherapy for unresectable colorectal peritoneal metastases: A single-arm phase II trial (CRC-PIPAC-II).

BACKGROUND: Palliative systemic therapy alternated with electrostatic precipitation oxaliplatin-based pressurized intraperitoneal aerosol chemotherapy (ePIPAC) has never been prospectively investigated in patients with unresectable colorectal peritoneal metastases (CPM). The CRC-PIPAC-II study aimed to assess safety, feasibility and efficacy of such bidirectional therapy. METHODS: This two-center, single-arm, phase II trial enrolled chemotherapy-naïve patients to undergo three treatment cycles, consisting of systemic therapy (CAPOX, FOLFOX, FOLFIRI, or FOLFOXIRI, all with bevacizumab) and oxaliplatin-based ePIPAC (92 mg/m2) with intravenous leucovorin (20 mg/m2) and 5-fluorouracil (400 mg/m2). Primary outcome were major treatment-related adverse events. Secondary outcomes included minor events, tumor response, progression-free survival (PFS) and overall survival (OS). RESULTS: Twenty patients completed 52 treatment cycles. Fifteen major events occurred in 7 patients (35 %): 5 events (33 %) related to systemic therapy; 5 (33 %) related to ePIPAC; and 5 (33 %) were biochemical events. No treatment-related deaths occurred. All patients experienced minor events, mostly abdominal pain, nausea and peripheral sensory neuropathy. After treatment, radiological, pathological, cytological, and biochemical response was observed in 0 %, 88 %, 38 %, and 31 % of patients respectively. Curative surgery was achieved in one patient. Median PFS was 10.0 months (95 % confidence interval [CI] 8.0-13.0) and median OS was 17.5 months (95 % CI 13.0-not reached). CONCLUSIONS: Combining palliative systemic therapy with oxaliplatin-based ePIPAC in patients with unresectable CPM was feasible and showed an acceptable safety profile. Treatment-induced response and survival are promising, yet further research is required to determine the additional value of ePIPAC to systemic therapy.

The Impact of Expectation Management and Model Transparency on Radiologists' Trust and Utilization of AI Recommendations for Lung Nodule Assessment on Computed Tomography: Simulated Use Study.

BACKGROUND: Many promising artificial intelligence (AI) and computer-aided detection and diagnosis systems have been developed, but few have been successfully integrated into clinical practice. This is partially owing to a lack of user-centered design of AI-based computer-aided detection or diagnosis (AI-CAD) systems. OBJECTIVE: We aimed to assess the impact of different onboarding tutorials and levels of AI model explainability on radiologists' trust in AI and the use of AI recommendations in lung nodule assessment on computed tomography (CT) scans. METHODS: In total, 20 radiologists from 7 Dutch medical centers performed lung nodule assessment on CT scans under different conditions in a simulated use study as part of a 2×2 repeated-measures quasi-experimental design. Two types of AI onboarding tutorials (reflective vs informative) and 2 levels of AI output (black box vs explainable) were designed. The radiologists first received an onboarding tutorial that was either informative or reflective. Subsequently, each radiologist assessed 7 CT scans, first without AI recommendations. AI recommendations were shown to the radiologist, and they could adjust their initial assessment. Half of the participants received the recommendations via black box AI output and half received explainable AI output. Mental model and psychological trust were measured before onboarding, after onboarding, and after assessing the 7 CT scans. We recorded whether radiologists changed their assessment on found nodules, malignancy prediction, and follow-up advice for each CT assessment. In addition, we analyzed whether radiologists' trust in their assessments had changed based on the AI recommendations. RESULTS: Both variations of onboarding tutorials resulted in a significantly improved mental model of the AI-CAD system (informative P=.01 and reflective P=.01). After using AI-CAD, psychological trust significantly decreased for the group with explainable AI output (P=.02). On the basis of the AI recommendations, radiologists changed the number of reported nodules in 27 of 140 assessments, malignancy prediction in 32 of 140 assessments, and follow-up advice in 12 of 140 assessments. The changes were mostly an increased number of reported nodules, a higher estimated probability of malignancy, and earlier follow-up. The radiologists' confidence in their found nodules changed in 82 of 140 assessments, in their estimated probability of malignancy in 50 of 140 assessments, and in their follow-up advice in 28 of 140 assessments. These changes were predominantly increases in confidence. The number of changed assessments and radiologists' confidence did not significantly differ between the groups that received different onboarding tutorials and AI outputs. CONCLUSIONS: Onboarding tutorials help radiologists gain a better understanding of AI-CAD and facilitate the formation of a correct mental model. If AI explanations do not consistently substantiate the probability of malignancy across patient cases, radiologists' trust in the AI-CAD system can be impaired. Radiologists' confidence in their assessments was improved by using the AI recommendations.

Dutch national guidelines for locally recurrent rectal cancer.

Due to improvements in treatment for primary rectal cancer, the incidence of LRRC has decreased. However, 6-12% of patients will still develop a local recurrence. Treatment of patients with LRRC can be challenging, because of complex and heterogeneous disease presentation and scarce - often low-grade - data steering clinical decisions. Previous consensus guidelines have provided some direction regarding diagnosis and treatment, but no comprehensive guidelines encompassing all aspects of the clinical management of patients with LRRC are available to date. The treatment of LRRC requires a multidisciplinary approach and overarching expertise in all domains. This broad expertise is often limited to specific expert centres, with dedicated multidisciplinary teams treating LRRC. A comprehensive, narrative literature review was performed and used to develop the Dutch National Guideline for management of LRRC, in an attempt to guide decision making for clinicians, regarding the complete clinical pathway from diagnosis to surgery.

Accuracy of MRI-ultrasound fusion-guided and systematic biopsy of the prostate.

OBJECTIVES: Prostate multiparametric MRI (mpMRI) with subsequent targeted biopsy of suspicious lesions has a critical role in the diagnostic workup of prostate cancer. The objective was to evaluate the diagnostic accuracy of systematic biopsies, targeted biopsies, and the combination of both in prostate cancer detection. METHODS: From January 1, 2013 to June 1, 2022, biopsy-naïve and prior biopsy-negative patients who underwent both systematic and targeted biopsies were included. MRIs were evaluated according to PI-RADS with biopsy threshold set at PI-RADS ≥3. Systematic biopsies consisted of 8-12 cores, based on prostate volume. Overall prostate cancer and clinically significant cancer (Gleason Score ≥3 + 4) detection rates were stratified based on PI-RADS and location within the prostate, and compared between biopsy types using McNemar test. RESULTS: Among 867 patients, 615 had prostate cancer, with 434 clinically significant cases. Overall detection rates were: PI-RADS 3 48%, PI-RADS 4 72%, and PI-RADS 5 90%. Detection rates for clinically significant cancer were 21%, 53%, and 72%, respectively. The combination of biopsy methods was most accurate in detecting clinically significant prostate cancer (P < .001). Targeted biopsies alone detected more clinically significant prostate cancer than systematic biopsies alone (43.1% vs 40.3%, P = .046). For posterior PI-RADS 5 lesions, no statistically significant difference was found between all biopsy methods. CONCLUSIONS: In the detection of clinically significant prostate cancer, the combination of systematic and targeted biopsies proves most effective. Targeted biopsies rarely missed significant cancer for posterior PI-RADS 5 lesions, suggesting systematic biopsies could be reserved for instances where targeted biopsy results are negative. ADVANCES IN KNOWLEDGE: This study emphasizes on the efficacy of mpMRI and targeted biopsies in suspected prostate cancer in real-world clinical context. For PI-RADS 5 lesions, systematic biopsies provide limited clinical benefit and may only be necessary when targeted biopsy results are negative.

Prognostic significance of MRI-detected extramural venous invasion according to grade and response to neo-adjuvant treatment in locally advanced rectal cancer A national cohort study after radiologic training and reassessment.

BACKGROUND: Detection of grade 3-4 extra mural venous invasion (mrEMVI) on magnetic resonance imaging (MRI) is associated with an increased distant metastases (DM)-rate. This study aimed to determine the impact of different grades of mrEMVI and their disappearance after neoadjuvant therapy. METHODS: A Dutch national retrospective cross-sectional study was conducted, including patients who underwent resection for rectal cancer in 2016 from 60/69 hospitals performing rectal surgery. Patients with a cT3-4 tumour ≤8 cm from the anorectal junction were selected and their MRI-scans were reassessed by trained abdominal radiologists. Positive mrEMVI grades (3 and 4) were analyzed in regard to 4-year local recurrence (LR), DM, disease-free survival (DFS) and overall survival (OS). RESULTS: The 1213 included patients had a median follow-up of 48 months (IQR 30-54). Positive mrEMVI was present in 324 patients (27%); 161 had grade 3 and 163 had grade 4. A higher mrEMVI stage (grade 4 vs grade 3 vs no mrEMVI) increased LR-risk (21% vs 18% vs 7%, <0.001) and DM-risk (49% vs 30% vs 21%, p < 0.001) and decreased DFS (42% vs 55% vs 69%, p < 0.001) and OS (62% vs 76% vs 81%, p < 0.001), which remained independently associated in multivariable analysis. When mrEMVI had disappeared on restaging MRI, DM-rate was comparable to initial absence of mrEMVI (both 26%), whereas LR-rate remained high (22% vs 9%, p = 0.006). CONCLUSION: The negative oncological impact of mrEMVI on recurrence and survival rates was dependent on grading. Disappearance of mrEMVI on restaging MRI decreased the risk of DM, but not of LR.

The Additional Role of F18-FDG PET/CT in Characterizing MRI-Diagnosed Tumor Deposits in Locally Advanced Rectal Cancer.

Rationale: F18-FDG PET/CT may be helpful in baseline staging of patients with high-risk LARC presenting with vascular tumor deposits (TDs), in addition to standard pelvic MRI and CT staging. Methods: All patients with locally advanced rectal cancer that had TDs on their baseline MRI of the pelvis and had a baseline F18-FDG PET/CT between May 2016 and December 2020 were included in this retrospective study. TDs as well as lymph nodes identified on pelvic MRI were correlated to the corresponding nodular structures on a standard F18-FDG PET/CT, including measurements of nodular SUVmax and SUVmean. In addition, the effects of partial volume and spill-in on SUV measurements were studied. Results: A total number of 62 patients were included, in which 198 TDs were identified as well as 106 lymph nodes (both normal and metastatic). After ruling out partial volume effects and spill-in, 23 nodular structures remained that allowed for reliable measurement of SUVmax: 19 TDs and 4 LNs. The median SUVmax between TDs and LNs was not significantly different (p = 0.096): 4.6 (range 0.8 to 11.3) versus 2.8 (range 1.9 to 3.9). For the median SUVmean, there was a trend towards a significant difference (p = 0.08): 3.9 (range 0.7 to 7.8) versus 2.3 (range 1.5 to 3.4). Most nodular structures showing either an SUVmax or SUVmean ≥ 4 were characterized as TDs on MRI, while only two were characterized as LNs. Conclusions: SUV measurements may help in separating TDs from lymph node metastases or normal lymph nodes in patients with high-risk LARC.

The importance of integrating diagnostic modalities in patient selection for CRS-HIPEC in colorectal peritoneal metastases.

BACKGROUND: Despite thorough preoperative work-up for cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS-HIPEC), so called open-close (OC) procedures as a result of irresectable disease remain common. Currently, diagnostic laparoscopy (DLS) is considered the gold standard, and consequently overrules the results of computed tomography (CT) scans; however, certain regions of the abdomen are difficult to assess and postoperative adhesion formation may further compromise staging during DLS. PURPOSE: To determine whether better clinical assessment could be achieved by combining the results of DLS and preoperative CT scans during a multidisciplinary team (MDT) meeting. MATERIAL AND METHODS: All patients who were eligible for CRS-HIPEC after DLS, but eventually underwent an OC procedure between 2010 and 2018 were selected. Radiological reassessment of CT scans was performed and combined with assessment of the DLS during a MDT meeting. The MDT was blinded for the outcome of the procedure (OC vs. CRS-HIPEC). RESULTS: The majority of the OC procedures (69%) was correctly predicted by the MDT. In most patients (88%), this conclusion was based on the combination of the radiological and surgical peritoneal cancer index (PCI). CT was particularly accurate for detection of larger tumor deposits in the abdominal regions, as 84%-86% was detected. Assessment of lesions in the small bowel regions is troublesome; 72% of lesions are missed on the preoperative CT scan. CONCLUSIONS: A combination of radiological and surgical assessment of the PCI may lead to improved preoperative patient selection for CRS-HIPEC.

Predictors of re-attendance at biennial screening mammography following a false positive referral: A study among women in the south of the Netherlands.

AIM: A false positive (FP) referral after screening mammography may influence a woman's likelihood to re-attend the screening program. The impact of having a FP result in the first or subsequent screening round on re-attendance after a FP result was investigated. In addition, we aimed to study differences in re-attendance rates between women who underwent non-invasive and invasive additional examinations as part of the diagnostic work-up following a FP referral. METHODS: A consecutive series of 13,597 women with a FP referral following biennial screening mammography in the south of the Netherlands between 2009 and 2019 was included. RESULTS: The screening re-attendance rate was 81.2% after a FP referral, and 91.3% when also including women who had clinical mammographic follow-up. Women who received a FP referral in the first screening round were less likely to re-attend the screening programme in the following three years, compared to those with a FP test in any subsequent round (odds ratio (OR): 0.59, 95%-confidence interval (CI): 0.51-0.69). Women with a FP referral who underwent invasive examinations after referral were less likely to re-attend the screening programme than those who only received additional imaging (OR, 0.48; 95% CI 0.36-0.64). CONCLUSION: Women with a FP referral are less likely to re-attend the screening programme if this referral occurs at their first screening round or when they undergo invasive diagnostic workup. Hospitals and screening organizations should prioritize informing women about the importance of re-attending the programme following a FP referral.

Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.

Background Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited. Purpose To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience. Results Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range, <.001 to .04). Conclusions Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Omoumi and Richiardi in this issue.

Intraperitoneal irinotecan with concomitant FOLFOX and bevacizumab for patients with unresectable colorectal peritoneal metastases: protocol of the multicentre, open-label, phase II, INTERACT-II trial.

INTRODUCTION: The peritoneum is the second most affected organ for the dissemination of colorectal cancer (CRC). Patients with colorectal peritoneal metastases (CPM) face a poor prognosis, despite the majority of patients being treated with palliative systemic therapy. The efficacy of palliative systemic therapy is limited due to the plasma-peritoneum barrier. The poor prognosis of unresectable CPM patients has resulted in the development of new treatment strategies where systemic therapy is combined with local, intraperitoneal chemotherapy. In the recently published phase I study, the maximum tolerated dose and thus the recommended phase II dose of intraperitoneal irinotecan was investigated and determined to be 75 mg. In the present study, the overall survival after treatment with 75 mg irinotecan with concomitant mFOLFOX4 and bevacizumab will be investigated. MATERIALS AND METHODS: In this single-arm phase II study in two Dutch tertiary referral centres, 85 patients are enrolled. Eligibility criteria are an adequate performance status and organ function, histologically confirmed microsatellite stable and unresectable CPM, no previous palliative therapy for CRC, no systemic therapy<6 months for CRC prior to enrolment and no previous cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS and HIPEC). Patients will undergo a diagnostic laparoscopy as standard work-up for CPM and if the peritoneal disease is considered unresectable (eg, Peritoneal Cancer Index (PCI)>20, too extensive small bowel involvement), a peritoneal access port and a port-a-cath are placed for administration of intraperitoneal and intravenous chemotherapy, respectively. Patients may undergo up to 12 cycles of study treatment. Each cycle consists of intravenous mFOLFOX4 with bevacizumab and concomitant intraperitoneal irinotecan (75 mg), which is repeated every 2 weeks, with a maximum of 12 cycles. Modified FOLFOX-4 regimen consists of 85 mg/m2 oxaliplatin plus 200 mg/m2 LV and 5-FU 400 mg/m2 bolus on day 1 followed by 1600 mg/m2 5-FU as a 46 hours infusion. Study treatment ends after the 12th cycle, or earlier in case of disease progression or unacceptable toxicity. The primary outcome is overall survival and key secondary outcomes are progression-free survival, safety (measured by the amount of grade ≥3 adverse events (Common Terminology Criteria for Adverse Events V.5.0)), patient-reported outcomes and pharmacokinetics of irinotecan. It is hypothesised that the trial treatment will lead to a 4 month increase in overall survival; from a median of 12.2 to 16.2 months. ETHICS AND DISSEMINATION: This study is approved by the Dutch Authority (CCMO, the Hague, the Netherlands), by a central medical ethics committee (MEC-U, Nieuwegein, the Netherlands) and by the institutional research boards of both research centres. Results will be submitted for publication in peer-reviewed medical journals and presented to patients and healthcare professionals. TRIAL REGISTRATION NUMBER: NCT06003998.

Abandonment of Routine Radiotherapy for Nonlocally Advanced Rectal Cancer and Oncological Outcomes.

Importance: Neoadjuvant short-course radiotherapy was routinely applied for nonlocally advanced rectal cancer (cT1-3N0-1M0 with >1 mm distance to the mesorectal fascia) in the Netherlands following the Dutch total mesorectal excision trial. This policy has shifted toward selective application after guideline revision in 2014. Objective: To determine the association of decreased use of neoadjuvant radiotherapy with cancer-related outcomes and overall survival at a national level. Design, Setting, and Participants: This multicenter, population-based, nationwide cross-sectional cohort study analyzed Dutch patients with rectal cancer who were treated in 2011 with a 4-year follow-up. A similar study was performed in 2021, analyzing all patients that were surgically treated in 2016. From these cohorts, all patients with cT1-3N0-1M0 rectal cancer and radiologically unthreatened mesorectal fascia were included in the current study. The data of the 2011 cohort were collected between May and October 2015, and the data of the 2016 cohort were collected between October 2020 and November 2021. The data were analyzed between May and October 2022. Main Outcomes and Measures: The main outcomes were 4-year local recurrence and overall survival rates. Results: Among the 2011 and 2016 cohorts, 1199 (mean [SD] age, 68 [11] years; 430 women [36%]) of 2095 patients (57.2%) and 1576 (mean [SD] age, 68 [10] years; 547 women [35%]) of 3057 patients (51.6%) had cT1-3N0-1M0 rectal cancer and were included, with proportions of neoadjuvant radiotherapy of 87% (2011) and 37% (2016). Four-year local recurrence rates were 5.8% and 5.5%, respectively (P = .99). Compared with the 2011 cohort, 4-year overall survival was significantly higher in the 2016 cohort (79.6% vs 86.4%; P < .001), with lower non-cancer-related mortality (13.8% vs 6.3%; P < .001). Conclusions and Relevance: The results of this cross-sectional study suggest that an absolute 50% reduction in radiotherapy use for nonlocally advanced rectal cancer did not compromise cancer-related outcomes at a national level. Optimizing clinical staging and surgery following the Dutch total mesorectal excision trial has potentially enabled safe deintensification of treatment.

A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes.

Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This retrospective multicentre cohort study examined 196 patients diagnosed with rectal cancer between 2008 and 2020 from three tertiary centres in the Netherlands. Primary and restaging T2W magnetic resonance imaging and clinical features were used. Visible LLNs were segmented and used for a multi-channel convolutional neural network. A deep learning model was developed and trained for the prediction of (L)LR according to malignant LLNs. Combined imaging and clinical features resulted in AUCs of 0.78 and 0.80 for LR and LLR, respectively. The sensitivity and specificity were 85.7% and 67.6%, respectively. Class activation map explainability methods were applied and consistently identified the same high-risk regions with structural similarity indices ranging from 0.772-0.930. This model resulted in good predictive value for (L)LR rates and can form the basis of future auto-segmentation programs to assist in the identification of high-risk patients and the development of risk stratification models.

Diagnostic accuracy of CT for local staging of colon cancer: A nationwide study in the Netherlands.

OBJECTIVE: To determine the accuracy of computed tomography (CT)-based staging in selecting high-risk colon cancer patients who would benefit from neoadjuvant chemotherapy while avoiding overtreatment. METHODS: Data of adult patients diagnosed with non-metastatic primary colon cancer in 2005-2020, who underwent surgical resection without neoadjuvant chemotherapy, were retrospectively collected from the Netherlands Cancer Registry. Agreement between clinical and pathological evaluation for each T and N stage was calculated. Sensitivity and specificity analyses were conducted to predict T3-T4 and N1-N2 stages, with histopathology as the reference standard. RESULTS: Data from 44,471 patients (median age, 71 years, 50% female) were evaluated. We included 38,915 patients with complete T stage and 39,565 patients with complete N stage for analyses. The overall clinical-pathological agreement for T stage was 59% and for N stage 57%. The sensitivity and specificity of CT to detect T3-T4 tumours were 80% (95% confidence interval (CI): 0.79, 0.80) and 76% (95% CI: 0.75, 0.77), respectively, with a positive predictive value (PPV) of 92% (95% CI: 0.92, 0.92). The sensitivity and specificity of CT to detect N1-N2 category were 62% (95% CI: 0.61, 0.63) and 70% (95% CI: 0.69, 0.71), respectively, with PPV 60% (95% CI: 0.59, 0.60). CONCLUSION: CT-based staging shows limited accuracy in selecting colon cancer patients who would benefit from neoadjuvant therapy without risking overtreatment. Detection of lymph node metastases with CT remains unreliable.

Causes and consequences of delayed diagnosis in breast cancer screening with a focus on mammographic features and tumour characteristics.

PURPOSE: To study the prevalence, causes and consequences of delayed breast cancer diagnosis in the screening population. METHODS: This retrospective study was performed in women who underwent biennial screening mammography between January 1, 2009 and June 30, 2019. Patients were divided into 3 groups; screen-detectedbreast cancer (SDC) without a diagnostic delay, a primary diagnostic delay(i.e. missed cancer at previous screening round)and a delay in diagnostic work-up after recall. Women with a true interval cancer (IC; i.e. not visible on prior examinations) were excluded. Outcome parameters included mammographic and tumour characteristics, lymph node status and surgical treatment. RESULTS: In our sample of 4491 women with breast cancer (4292 SDC and 199 'missed' IC), respectively, a total of 1112 women experienced a diagnostic delay of ≥ 4 months. Compared to women without a diagnostic delay (n = 2720), the 176 women with a delay in diagnostic work-up showed overall similar mammographic abnormalities (P = 0.052). These groups show similar distributions in invasive tumours, tumour stage and lymph node status (P = 0.25, P = 0.95 and P = 0.93, respectively). Women with a primary diagnostic delay (n = 936) showed less calcifications (P < 0.001), and more masses with calcifications and architectural distortions on mammography (P = 0.01 and P = 0.04, respectively). Moreover, this group comprised larger tumours (P < 0.001) and lymph node metastases (P < 0.001), and more often underwent mastectomy (P < 0.001). CONCLUSIONS: A primary diagnostic delay in breast cancer diagnosis results in less favourable tumour characteristics and relatively more mastectomies compared to no delay in breast cancer diagnosis and a delay in diagnostic work-up after recall.

Computer-Aided Detection for Pancreatic Cancer Diagnosis: Radiological Challenges and Future Directions.

Radiological imaging plays a crucial role in the detection and treatment of pancreatic ductal adenocarcinoma (PDAC). However, there are several challenges associated with the use of these techniques in daily clinical practice. Determination of the presence or absence of cancer using radiological imaging is difficult and requires specific expertise, especially after neoadjuvant therapy. Early detection and characterization of tumors would potentially increase the number of patients who are eligible for curative treatment. Over the last decades, artificial intelligence (AI)-based computer-aided detection (CAD) has rapidly evolved as a means for improving the radiological detection of cancer and the assessment of the extent of disease. Although the results of AI applications seem promising, widespread adoption in clinical practice has not taken place. This narrative review provides an overview of current radiological CAD systems in pancreatic cancer, highlights challenges that are pertinent to clinical practice, and discusses potential solutions for these challenges.

Locally recurrent rectal cancer: Oncological outcomes for patients with a pathological complete response after neoadjuvant therapy.

BACKGROUND: For patients with locally recurrent rectal cancer, it is an ongoing pursuit to establish factors predicting or improving oncological outcomes. In locally advanced rectal cancer, a pCR appears to be associated with improved outcomes. The aim of this retrospective cohort study was to compare the oncological outcomes of patients with locally recurrent rectal cancer with and without a pCR. METHODS: Patients who underwent neoadjuvant treatment and surgery for locally recurrent rectal cancer with curative intent between January 2004 and June 2020 at a tertiary referral hospital were analysed. Primary outcomes included overall survival, disease-free survival, metastasis-free survival, and local re-recurrence-free survival, stratified according to whether the patient had a pCR. RESULTS: Of a total of 345 patients, 51 (14.8 per cent) had a pCR. Median follow-up was 36 (i.q.r. 16-60) months. The 3-year overall survival rate was 77 per cent for patients with a pCR and 51.1 per cent for those without (P < 0.001). The 3-year disease-free survival rate was 56 per cent for patients with a pCR and 26.1 per cent for those without (P < 0.001). The 3-year local re-recurrence-free survival rate was 82 and 44 per cent respectively (P < 0.001). Surgical procedures (for example soft tissue, sacrum, and urogenital organ resections) and postoperative complications were comparable between patients with and without a pCR. CONCLUSION: This study showed that patients with a pCR have superior oncological outcomes to those without a pCR. It may therefore be safe to consider a watch-and-wait approach in highly selected patients, potentially improving quality of life by omitting extensive surgical procedures without compromising oncological outcomes.

The Effects of Artificial Intelligence Assistance on the Radiologists' Assessment of Lung Nodules on CT Scans: A Systematic Review.

To reduce the number of missed or misdiagnosed lung nodules on CT scans by radiologists, many Artificial Intelligence (AI) algorithms have been developed. Some algorithms are currently being implemented in clinical practice, but the question is whether radiologists and patients really benefit from the use of these novel tools. This study aimed to review how AI assistance for lung nodule assessment on CT scans affects the performances of radiologists. We searched for studies that evaluated radiologists' performances in the detection or malignancy prediction of lung nodules with and without AI assistance. Concerning detection, radiologists achieved with AI assistance a higher sensitivity and AUC, while the specificity was slightly lower. Concerning malignancy prediction, radiologists achieved with AI assistance generally a higher sensitivity, specificity and AUC. The radiologists' workflows of using the AI assistance were often only described in limited detail in the papers. As recent studies showed improved performances of radiologists with AI assistance, AI assistance for lung nodule assessment holds great promise. To achieve added value of AI tools for lung nodule assessment in clinical practice, more research is required on the clinical validation of AI tools, impact on follow-up recommendations and ways of using AI tools.

Analysis of computer-aided diagnostics in the preoperative diagnosis of ovarian cancer: a systematic review.

OBJECTIVES: Different noninvasive imaging methods to predict the chance of malignancy of ovarian tumors are available. However, their predictive value is limited due to subjectivity of the reviewer. Therefore, more objective prediction models are needed. Computer-aided diagnostics (CAD) could be such a model, since it lacks bias that comes with currently used models. In this study, we evaluated the available data on CAD in predicting the chance of malignancy of ovarian tumors. METHODS: We searched for all published studies investigating diagnostic accuracy of CAD based on ultrasound, CT and MRI in pre-surgical patients with an ovarian tumor compared to reference standards. RESULTS: In thirty-one included studies, extracted features from three different imaging techniques were used in different mathematical models. All studies assessed CAD based on machine learning on ultrasound, CT scan and MRI scan images. Per imaging method, subsequently ultrasound, CT and MRI, sensitivities ranged from 40.3 to 100%; 84.6-100% and 66.7-100% and specificities ranged from 76.3-100%; 69-100% and 77.8-100%. Results could not be pooled, due to broad heterogeneity. Although the majority of studies report high performances, they are at considerable risk of overfitting due to the absence of an independent test set. CONCLUSION: Based on this literature review, different CAD for ultrasound, CT scans and MRI scans seem promising to aid physicians in assessing ovarian tumors through their objective and potentially cost-effective character. However, performance should be evaluated per imaging technique. Prospective and larger datasets with external validation are desired to make their results generalizable.

Intraoperative Ultrasound During Surgical Exploration in Patients with Pancreatic Cancer and Vascular Involvement (ULTRAPANC): A Prospective Multicenter Study.

BACKGROUND: Determining the resectability of pancreatic cancer with vascular involvement on preoperative computed tomography imaging remains challenging, especially following preoperative chemotherapy and chemoradiotherapy. Intraoperative ultrasound (IOUS) may provide real-time additional information, but prospective multicenter series confirming its value are lacking. PATIENTS AND METHODS: This prospective multicenter study included patients undergoing surgical exploration for pancreatic cancer with vascular involvement. All patients underwent IOUS at the start of explorative laparotomy. Primary outcomes were resectability status as defined by the National Comprehensive Cancer Network and the extent of vascular involvement. RESULTS: Overall, 85 patients were included, of whom 74 (87%) were post preoperative chemotherapy, and mostly following FOLFIRINOX regimen (n = 57; 76%). On the basis of preoperative imaging, 34 (40%) patients were staged as resectable (RPC), 32 (38%) borderline resectable (BRPC), and 19 (22%) locally advanced pancreatic cancer (LAPC). IOUS changed the resectability status in 32/85 (38%) patients (p < 0.001), including 8/19 (42%) patients with LAPC who were downstaged (4 to BRPC, 4 to RPC), and 22/32 (69%) patients with BRPC who were downstaged to RPC. Among patients with presumed superior mesenteric artery (SMA) involvement, 20/28 (71%) had no SMA involvement on IOUS. In 15 of these 20 patients a pancreatic resection was performed, all with R0 SMA margin. CONCLUSION: IOUS during surgical exploration for pancreatic cancer and vascular involvement downstaged the resectability status in over one-third of patients, which could facilitate progress during surgical exploration. This finding should be confirmed by larger studies, including detailed pathology assessment. Trial Registration www.trialregister.nl (NL7621).