Computer-aided diagnosis significantly reduces the low-dose CT screening false-positive rate and increases the positive predictive value of lung nodule evaluation. Purpose To test whether computer-aided diagnosis (CAD) approaches can increase the positive predictive value (PPV) and reduce the false-positive rate in lung cancer screening for small nodules compared with human reading by thoracic radiologists. Materials and Methods A matched case-control sample of low-dose computed tomography (CT) studies in 186 participants with 4–20-mm noncalcified lung nodules who underwent biopsy in the National Lung Screening Trial (NLST) was selected. Variables used for matching were age, sex, smoking status, chronic obstructive pulmonary disease status, body mass index, study year of the positive screening test, and screening results. Studies before lung biopsy were randomly split into a training set (70 cancers plus 70 benign controls) and a validation set (20 cancers plus 26 benign controls). Image features from within and outside dominant nodules were extracted. A CAD algorithm developed from the training set and a random forest classifier were applied to the validation set t...

Current lung cancer screening guidelines use mean diameter, volume or density of the largest lung nodule in the prior computed tomography (CT) or appearance of new nodule to determine the timing of the next CT. We aimed at developing a more accurate screening protocol by estimating the 3-year lung cancer risk after two screening CTs using deep machine learning (ML) of radiologist CT reading and other universally available clinical information. A deep machine learning (ML) algorithm was developed from 25,097 participants who had received at least two CT screenings up to two years apart in the National Lung Screening Trial. Double-blinded validation was performed using 2,294 participants from the Pan-Canadian Early Detection of Lung Cancer Study (PanCan). Performance of ML score to inform lung cancer incidence was compared with Lung-RADS and volume doubling time using time-dependent ROC analysis. Exploratory analysis was performed to identify individuals with aggressive cancers and higher mortality rates. In the PanCan validation cohort, ML showed excellent discrimination with a 1-, 2- and 3-year time-dependent AUC values for cancer diagnosis of 0·968±0·013, 0·946±0·013 and 0·899±0·017. Although high ML score cohort included only 10% of the PanCan sample, it identified 94%, 85%, and 71% of incident and interval lung cancers diagnosed within 1, 2, and 3 years, respectively, after the second screening CT. Furthermore, individuals with high ML score had significantly higher mortality rates (HR=16·07, p<0·001) compared to those with lower risk. ML tool that recognizes patterns in both temporal and spatial changes as well as synergy among changes in nodule and non-nodule features may be used to accurately guide clinical management after the next scheduled repeat screening CT.

Purpose: To quantify the accuracy of amide proton transfer-weighted (APTw) MRI for identifying active glioma post-treatment via radiographically guided stereotactic tissue validation. Experimental Design: Twenty-one patients referred for surgery for MRI features concerning for tumor progression versus treatment effect underwent pre-operative APTw imaging. Stereotactic biopsies were taken from regions of interest with varying APTw signal intensities. The relationship between final clinical pathology as well as the histopathology of each of the 64 specimens was analyzed relative to APTw results. Analysis of confirmed recurrent tumor or treatment effect tissue was used to perform receiver-operating-characteristic (ROC) analysis. Results: Eighteen of 21 patients had recurrent tumor, and 3 had treatment effect on clinical pathology. In 12 patients, there were multiple histopathologic assignments confirmed within the same tumor. Of the 64 total specimens, 20 specimens were active glioma, 27 mixed active and quiescent glioma, and 17 quiescent/no identifiable tumor. APTw signal intensity and histopathologic assignment, cellularity, and proliferation index had significant positive correlations (R = 0.651, 0.580, and 0.458, respectively; all P < 0.001). ROC analysis with a 1.79% APTw intensity cutoff differentiated active from non-active tumor (AUC of 0.881) with 85.1% sensitivity and 94.1% specificity. Analysis of clinical pathology showed the mean APTw intensity for each patient had 94.4% sensitivity and 100% positive predictive value for identifying recurrent glioma at this cutoff. Conclusions: APTw imaging hyperintensity may be a marker of active malignant glioma. It is able to distinguish between regions of heterogeneous abnormality on anatomical brain MRI with high sensitivity and specificity.

Objective Neoadjuvant therapy increases rates of margin-negative resection of borderline resectable pancreatic ductal adenocarcinoma (BL-PDAC). Criteria for BL-PDAC resection following neoadjuvant chemotherapy and radiation therapy (NCRT) have not been clearly defined. Methods Fifty consecutive patients with BL-PDAC who received NCRT from 2007 to 2012 were identified. Computed tomography (CT) scans pre- and post-treatment were centrally reviewed. Results Twenty-nine patients (58 %) underwent resection following NCRT, while 21 (42 %) remained unresected. Patients selected for and successfully undergoing resection were more likely to have better performance status and absence of the following features on pre- and post-treatment CT: superior mesenteric vein/portal vein encasement, superior mesenteric artery involvement, tumor involvement of two or more vessels, and questionable/overt metastases (all p < 0.05). Tumor volume and degree of tumor–vessel involvement did not significantly change in both groups after NCRT (all p > 0.05). The median overall survival was 22.9 months in resected versus 13.0 months in unresected patients (p < 0.001). Of patients undergoing resection, 93 % were margin-negative, 72 % were node-negative, and 54 % demonstrated moderate pathologic response to NCRT. Conclusion Apparent radiographic extent of vascular involvement does not change significantly after NCRT. Patients without metastatic disease should be chosen for surgical exploration based on adequate performance status and lack of disease progression.

Elucidating the earliest pathogenic steps in cancer development is fundamental to improving its early detection and prevention. Ovarian high-grade serous carcinoma (HGSC), a highly aggressive cancer, mostly originates from the fallopian tube epithelium through a precursor stage, serous tubal intraepithelial carcinoma (STIC). In this study, we performed spatial transcriptomic analysis to compare STICs, carcinoma, and their matched normal fallopian tube epithelium. Several differentially expressed genes in STICs and carcinomas were involved in cancer metabolism and detected in a larger independent transcriptomic dataset of ovarian HGSCs. Among these, insulin-like growth factor binding protein-2 (IGFBP2) was found to undergo DNA hypomethylation and to be increased at the protein level in STICs. Pyrosequencing revealed an association of IGFBP2 expression with the methylation state of its proximal enhancer, and 5-azacytidine treatment increased IGFBP2 expression. In postmenopausal fallopian tubes, where most STICs are detected, IGFBP2 immunoreactivity was detected in all 38 proliferatively active STICs but was undetectable in morphologically normal tubal epithelia, including those with TP53 mutations. In premenopausal fallopian tubes, IGFBP2 expression was limited to the secretory epithelium at the proliferative phase, and estradiol treatment increased IGFBP2 expression levels. IGFBP2 knockdown suppressed the growth of IGFBP2-expressing tubal epithelial cells via inactivation of the AKT pathway. Taken together, demethylation of the proximal enhancer of IGFBP2 drives tumor development by maintaining the increased IGFBP2 required for proliferation in an otherwise estrogen-deprived, proliferation-quiescent, and postmenopausal tubal microenvironment. Significance: Molecular studies of the earliest precursor lesions of ovarian cancer reveal a role of IGFBP2 in propelling tumor initiation, providing new insights into ovarian cancer development.

Serous tubal intraepithelial carcinoma (STIC) is the fallopian tube precursor lesion for most cases of pelvic high-grade serous carcinoma (HGSC). To date, the morphologic, molecular, and clinical heterogeneity of STIC and a less atypical putative precursor lesion, termed serous tubal intraepithelial lesion, has not been well characterized. Better understanding of precursor heterogeneity could impact the clinical management of women with incidental STICs (without concurrent carcinoma) identified in cases of prophylactic or opportunistic salpingectomy. This study analyzed morphologic and molecular features of 171 STICs and 21 serous tubal intraepithelial lesions. We assessed their histologic features, Ki-67 and p53 staining patterns, and genome-wide DNA copy number alterations. We classified all precursor lesions into 2 morphologic subtypes, one with a flat surface (Flat) and the other characterized by budding, loosely adherent, or detached (BLAD) morphology. On the basis of pathology review by a panel of 8 gynecologic pathologists, we found 87 BLAD, 96 Flat, and 9 indeterminate lesions. As compared with Flat lesions, BLAD lesions were more frequently diagnostic of STIC (P<0.0001) and were found concurrently with HGSC (P<0.0001). BLAD morphology was also characterized by higher Ki-67 proliferation index (P<0.0001), presence of epithelial stratification (P<0.0001), and increased lymphocyte density (P<0.0001). BLAD lesions also exhibited more frequent DNA copy number gain/amplification at the CCNE1 or CMYC loci canonical to HGSCs (P<0.0001). Both BLAD morphology and STIC diagnoses are independent risk factors for an elevated Ki-67 proliferation index. No correlation was observed between BLAD and Flat lesions with respect to patient age, presence of germline BRCA1/2 mutation, or p53 staining pattern. These findings suggest that tubal precursor lesions are morphologically and molecularly heterogeneous, laying the foundation for further studies on the pathogenesis of HGSC initiation and identifying histologic features predictive of poor patient outcomes.