Deep learning assisted mitotic counting for breast cancer.

As part of routine histological grading, for every invasive breast cancer the mitotic count is assessed by counting mitoses in the (visually selected) region with the highest proliferative activity. Because this procedure is prone to subjectivity, the present study compares visual mitotic counting with deep learning based automated mitotic counting and fully automated hotspot selection. Two cohorts were used in this study. Cohort A comprised 90 prospectively included tumors which were selected based on the mitotic frequency scores given during routine glass slide diagnostics. This pathologist additionally assessed the mitotic count in these tumors in whole slide images (WSI) within a preselected hotspot. A second observer performed the same procedures on this cohort. The preselected hotspot was generated by a convolutional neural network (CNN) trained to detect all mitotic figures in digitized hematoxylin and eosin (H&E) sections. The second cohort comprised a multicenter, retrospective TNBC cohort (n = 298), of which the mitotic count was assessed by three independent observers on glass slides. The same CNN was applied on this cohort and the absolute number of mitotic figures in the hotspot was compared to the averaged mitotic count of the observers. Baseline interobserver agreement for glass slide assessment in cohort A was good (kappa 0.689; 95% CI 0.580-0.799). Using the CNN generated hotspot in WSI, the agreement score increased to 0.814 (95% CI 0.719-0.909). Automated counting by the CNN in comparison with observers counting in the predefined hotspot region yielded an average kappa of 0.724. We conclude that manual mitotic counting is not affected by assessment modality (glass slides, WSI) and that counting mitotic figures in WSI is feasible. Using a predefined hotspot area considerably improves reproducibility. Also, fully automated assessment of mitotic score appears to be feasible without introducing additional bias or variability.

[Atypical presentation of male breast cancer]. / Atypische presentatie van borstkanker bij een man.

BACKGROUND: Approximately 1% of all breast cancers occur in men. With an annual incidence of 130 cases in the Netherlands, the occurrence of male breast cancer is rare. CASE DESCRIPTION: We report the case of a 72-year-old male who was referred to a breast outpatient clinic for the evaluation of a multinodular skin lesion of the nipple. The nipple lesion was found to be an invasive carcinoma of the breast with neuroendocrine differentiation. Retrospectively, a breast abnormality could be detected on radiologic imaging 2 years prior to cancer diagnosis. CONCLUSION: Breast cancer in men is associated with an increased diagnostic delay compared to women and is subsequently diagnosed at a later stage. Studies on the survival of breast cancer report worse survival in men compared to women. Health care professionals should be alerted to the presence of a malignancy when dealing with abnormalities of the male breast.

Suprainguinal Re-Resection of the Lateral Femoral Cutaneous Nerve in Persistence or Recurrence of Meralgia Paresthetica After Previous Transection: Results of a Case Series.

OBJECTIVE: Suprainguinal re-resection of the proximal nerve stump can be performed in case of persistent or recurrent symptoms of meralgia paresthetica after previous transection of the lateral femoral cutaneous nerve (LFCN). Currently, no long-term results for this procedure have been reported in the literature. METHODS: In this study, 20 consecutive patients with persistent (13 cases) or recurrent (7 cases) symptoms of meralgia paresthetica were reoperated at a mean interval of 16 months after the first transection of the LFCN. The proximal nerve stump was sent for histopathologic analysis of a potential traumatic neuroma. Outcome was assessed using a 5-point Likert scale, which was obtained at a mean interval of 3.5 years after the suprainguinal re-resection. RESULTS: The proximal stump of the LFCN was identified in 90% of the cases. Successful pain relief (Likert 1 or 2) was obtained in 65% of the patients. A neuroma was found in 11 cases (55%), mostly in recurrent cases after a pain-free interval. The indication for recurrence of symptoms more frequently resulted in successful pain relief (71%) compared with results for the indication for persistence of symptoms (62%). There was no correlation between the presence of a neuroma and the chance for pain relief. CONCLUSIONS: Suprainguinal re-resection of the LFCN can be a successful procedure, both for persistence and recurrence of symptoms of meralgia paresthetica after previous transection, with long-lasting pain relief. Several factors, however, should be considered before performing this relatively new technique in patients that are discussed in this article.

Optimizing Mutation and Fusion Detection in NSCLC by Sequential DNA and RNA Sequencing.

INTRODUCTION: Frequently, patients with locally advanced or metastatic NSCLC are screened for mutations and fusions. In most laboratories, molecular workup includes a multitude of tests: immunohistochemistry (ALK, ROS1, and programmed death-ligand 1 testing), DNA sequencing, in situ hybridization for fusion, and amplification detection. With the fast-emerging new drugs targeting specific fusions and exon-skipping events, this procedure harbors a growing risk of tissue exhaustion. METHODS: In this study, we evaluated the benefit of anchored, multiplexed, polymerase chain reaction-based targeted RNA sequencing (RNA next-generation sequencing [NGS]) in the identification of gene fusions and exon-skipping events in patients, in which no pathogenic driver mutation was found by DNA-based targeted cancer hotspot NGS (DNA NGS). We analyzed a cohort of stage IV NSCLC cases from both in-house and referral hospitals, consisting 38.5% cytology samples and 61.5% microdissected histology samples, mostly core needle biopsies. We compared molecular findings in a parallel workup (DNA NGS and RNA NGS, cohort 1, n = 198) with a sequential workup (DNA NGS followed by RNA NGS in selected cases, cohort 2, n = 192). We hypothesized the sequential workup to be the more efficient procedure. RESULTS: In both cohorts, a maximum of one oncogenic driver mutation was found per case. This is in concordance with large, whole-genome databases and suggests that it is safe to omit RNA NGS when a clear oncogenic driver is identified in DNA NGS. In addition, this reduced the number of necessary RNA NGS to only 53% of all cases. The tumors of never smokers, however, were enriched for fusions and exon-skipping events (32% versus 4% in former and current smokers, p = 0.00), and therefore benefited more often from the shorter median turnaround time of the parallel approach (15 d versus only 9 d in the parallel workup). CONCLUSIONS: We conclude that sequentially combining DNA NGS and RNA NGS is the most efficient strategy for mutation and fusion detection in smoking-associated NSCLC, whereas for never smokers we recommend a parallel approach. This approach was shown to be feasible on small tissue samples including for cytology tests, can drastically reduce the complexity and cost of molecular workup, and also provides flexibility in the constantly evolving landscape of actionable targets in NSCLC.

Deep learning and manual assessment show that the absolute mitotic count does not contain prognostic information in triple negative breast cancer.

PURPOSE: The prognostic value of mitotic count for invasive breast cancer is firmly established. As yet, however, limited studies have been aimed at assessing mitotic counts as a prognostic factor for triple negative breast cancers (TNBC). Here, we assessed the prognostic value of absolute mitotic counts for TNBC, using both deep learning and manual procedures. METHODS: A retrospective TNBC cohort (n = 298) was used. The absolute manual mitotic count was assessed by averaging counts from three independent observers. Deep learning was performed using a convolutional neural network on digitized H&E slides. Multivariable Cox regression models for relapse-free survival and overall survival served as baseline models. These were expanded with dichotomized mitotic counts, attempting every possible cut-off value, and evaluated by means of the c-statistic. RESULTS: We found that per 2 mm2 averaged manual mitotic counts ranged from 1 to 187 (mean 37.6, SD 23.4), whereas automatic counts ranged from 1 to 269 (mean 57.6; SD 42.2). None of the cut-off values improved the models' baseline c-statistic, for both manual and automatic assessments. CONCLUSIONS: Based on our results we conclude that the level of proliferation, as reflected by mitotic count, does not serve as a prognostic factor for TNBC. Therefore, TNBC patient management based on mitotic count should be discouraged.

[Von Meyenburg complexes in the liver: not metastases]. / Von meyenburg-complexen in de lever: geen metastasen.

A 74-year-old woman underwent a laparotomy for a rectal carcinoma. Multiple lesions of the liver were discovered as incidental findings. Histopathology revealed that these were Von Meyenburg complexes (VMCs). VMCs, also called biliary hamartomas, are rare and benign malformations of the bile ducts. The lesions present as diffuse greyish-white to greyish-yellow or black nodules of the liver, which on gross inspection and in radiological examinations strongly resemble liver metastases. VMCs are mostly asymptomatic and therefore often an incidental finding at laparotomy or post-mortem examination. The prevalence of VMC is age dependent and is 5.6% in adult patients at post-mortem examination. VMCs are sometimes associated with cholangiocarcinoma. Diagnostic imaging of VMC is difficult and of little specificity. Intraoperative frozen section analysis to differentiate between malignant and benign lesions has a sensitivity of 97% and a specificity of 99%. The benign nature of VMCs means that they do not require treatment. The patient underwent total mesorectal excision and follow-up after 3, 7 and 9 months did not reveal any indications of recurrent colorectal cancer or metastases.