Artificial intelligence in cancer imaging: Clinical challenges and applications.

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

Synthetic lethal interaction between oncogenic KRAS dependency and STK33 suppression in human cancer cells.

An alternative to therapeutic targeting of oncogenes is to perform "synthetic lethality" screens for genes that are essential only in the context of specific cancer-causing mutations. We used high-throughput RNA interference (RNAi) to identify synthetic lethal interactions in cancer cells harboring mutant KRAS, the most commonly mutated human oncogene. We find that cells that are dependent on mutant KRAS exhibit sensitivity to suppression of the serine/threonine kinase STK33 irrespective of tissue origin, whereas STK33 is not required by KRAS-independent cells. STK33 promotes cancer cell viability in a kinase activity-dependent manner by regulating the suppression of mitochondrial apoptosis mediated through S6K1-induced inactivation of the death agonist BAD selectively in mutant KRAS-dependent cells. These observations identify STK33 as a target for treatment of mutant KRAS-driven cancers and demonstrate the potential of RNAi screens for discovering functional dependencies created by oncogenic mutations that may enable therapeutic intervention for cancers with "undruggable" genetic alterations.

Improved optic nerve visualization and treatment planning through a dedicated optic nerve MRI protocol.

OBJECTIVE: This study describes an innovative optic nerve MRI protocol for better delineating optic nerve anatomy from neighboring pathology. METHODS: Twenty-two patients undergoing MRI examination of the optic nerve with the dedicated protocol were identified and included for analysis of imaging, surgical strategy, and outcomes. T2-weighted and fat-suppressed T1-weighted gadolinium-enhanced images were acquired perpendicular and parallel to the long axis of the optic nerve to achieve en face and in-line views along the course of the nerve. RESULTS: Dedicated optic nerve MRI sequences provided enhanced visualization of the nerve, CSF within the nerve sheath, and local pathology. Optic nerve sequences leveraged the "CSF ring" within the optic nerve sheath to create contrast between pathology and normal tissue, highlighting areas of compression. Tumor was readily tracked along the longitudinal axis of the nerve by images obtained parallel to the nerve. The findings augmented treatment planning. CONCLUSIONS: The authors present a dedicated optic nerve MRI protocol that is simple to use and affords improved cross-sectional and longitudinal visualization of the nerve, surrounding CSF, and pathology. This improved visualization enhances radiological evaluation and treatment planning for optic nerve lesions.

Chordoma: Genetics and Contemporary Management.

Chordomas, arising from notochord remnants, are rare neoplasms with aggressive growth patterns despite their histologically low-grade nature. This review explores their embryological origins, molecular markers like brachyury, and genetic alterations driving pathogenesis. Diagnosis relies on advanced imaging and biopsy confirmation due to overlapping features with chondrosarcoma. The WHO classification distinguishes conventional, dedifferentiated, and poorly differentiated chordomas, each with distinct prognostic implications. Recent genomic analyses uncovered recurrent mutations in PI3K signaling pathways and chromatin remodeling genes, informing prognostic models. Surgery remains the cornerstone of treatment, though adjuvant radiation complements surgical resection. Although chordomas are generally considered refractory to medical therapy, emerging targeted molecular strategies show potential promise in ongoing trials. This review aims to provide a concise yet comprehensive overview of chordomas, guiding clinicians in diagnosis, treatment, and prognostication for improved patient outcomes.

The Performance of Computer-Aided Detection Digital Chest X-ray Reading Technologies for Triage of Active Tuberculosis Among Persons With a History of Previous Tuberculosis.

BACKGROUND: Digital chest X-ray (dCXR) computer-aided detection (CAD) technology uses lung shape and texture analysis to determine the probability of tuberculosis (TB). However, many patients with previously treated TB have sequelae, which also distort lung shape and texture. We evaluated the diagnostic performance of 2 CAD systems for triage of active TB in patients with previously treated TB. METHODS: We conducted a retrospective analysis of data from a cross-sectional active TB case finding study. Participants ≥15 years, with ≥1 current TB symptom and complete data on history of previous TB, dCXR, and TB microbiological reference (Xpert MTB/RIF) were included. dCXRs were evaluated using CAD4TB (v.7.0) and qXR (v.3.0). We determined the diagnostic accuracy of both systems, overall and stratified by history of TB, using a single threshold for each system that achieved 90% sensitivity and maximized specificity in the overall population. RESULTS: Of 1884 participants, 452 (24.0%) had a history of previous TB. Prevalence of microbiologically confirmed TB among those with and without history of previous TB was 12.4% and 16.9%, respectively. Using CAD4TB, sensitivity and specificity were 89.3% (95% CI: 78.1-96.0%) and 24.0% (19.9-28.5%) and 90.5% (86.1-93.3%) and 60.3% (57.4-63.0%) among those with and without previous TB, respectively. Using qXR, sensitivity and specificity were 94.6% (95% CI: 85.1-98.9%) and 22.2% (18.2-26.6%) and 89.7% (85.1-93.2%) and 61.8% (58.9-64.5%) among those with and without previous TB, respectively. CONCLUSIONS: The performance of CAD systems as a TB triage tool is decreased among persons previously treated for TB.

Functional inhibition of deep brain non-visual opsins facilitates acute long day induction of reproductive recrudescence in male Japanese quail.

For nearly a century, we have known that brain photoreceptors regulate avian seasonal biology. Two photopigments, vertebrate ancient opsin (VA) and neuropsin (OPN5), provide possible molecular substrates for these photoreceptor pathways. VA fulfills many criteria for providing light input to the reproductive response, but a functional link has yet to be demonstrated. This study examined the role of VA and OPN5 in the avian photoperiodic response of Japanese quail (Coturnix japonica). Non-breeding male quail were housed under short days (6L:18D) and received an intracerebroventricular infusion of adeno-associated viral vectors with shRNAi that selectively inhibited either VA or OPN5. An empty viral vector acted as a control. Quail were then photostimulated (16L:8D) to stimulate gonadal growth. Two long days significantly increased pituitary thyrotrophin-stimulating hormone ß-subunit (TSHß) and luteinizing hormone ß-subunit (LHß) mRNA of VA shRNAi treated quail compared to controls. Furthermore, at one week there was a significant increase, compared to controls, in both hypothalamic gonadotrophin releasing hormone-I (GnRH-I) mRNA and paired testicular mass in VA shRNAi birds. Opn5 shRNAi facilitated the photoinduced increase in TSHß mRNA at 2 days, but no other differences were identified compared to controls. Contrary to our expectations, the silencing of deep brain photoreceptors enhanced the response of the reproductive axis to photostimulation rather than preventing it. In addition, we show that VA opsin plays a dominant role in the light-dependent neuroendocrine control of seasonal reproduction in birds. Together our findings suggest the photoperiodic response involves at least two photoreceptor types and populations working together with VA opsin playing a dominant role.

Surgical strategies for intracranial meningioma in the molecular era.

INTRODUCTION: Surgical resection has long been the treatment of choice for meningiomas and is considered curative in many cases. Indeed, the extent of resection (EOR) remains a significant factor in determining disease recurrence and outcome optimization for patients undergoing surgery. Although the Simpson Grading Scale continues to be widely accepted as the measure of EOR and is used to predict symptomatic recurrence, its utility is under increasing scrutiny. The influence of surgery in the definitive management of meningioma is being re-appraised considering the rapid evolution of our understanding of the biology of meningioma. DISCUSSION: Although historically considered "benign" lesions, meningioma natural history can vary greatly, behaving with unexpectedly high recurrence rates and growth which do not always behave in accordance with their WHO grade. Histologically confirmed WHO grade 1 tumors may demonstrate unexpected recurrence, malignant transformation, and aggressive behavior, underscoring the molecular complexity and heterogeneity. CONCLUSION: As our understanding of the clinical predictive power of genomic and epigenomic factors matures, we here discuss the importance of surgical decision-making paradigms in the context of our rapidly evolving understanding of these molecular features.

Assessment of association between lower ureteric excision technique and oncological outcomes for upper urinary tract urothelial carcinoma: retrospective analysis from the Scottish Renal Cancer Consortium.

PURPOSE: Nephroureterectomy(NU) remains the gold-standard surgical option for the management of upper urinary tract urothelial carcinoma(UTUC). Controversy exists regarding the optimal excision technique of the lower ureter. We sought to compare post-UTUC bladder tumour recurrence across the Scottish Renal Cancer Consortium(SRCC). METHODS: Patients who underwent NU for UTUC across the SRCC 2012-2019 were identified. The impact of lower-end surgical technique along with T-stage, N-stage, tumour location and focality, positive surgical margin, pre-NU ureteroscopy, upper-end technique and adjuvant mitomycin C administration were assessed by Kaplan-Meier and Cox-regression. The primary outcome was intra-vesical recurrence-free survival (B-RFS). RESULTS: In 402 patients, the median follow-up was 29 months. The lower ureter was managed by open transvesical excision in 90 individuals, transurethral and laparoscopic dissection in 76, laparoscopic or open extra-vesical excision in 31 and 42 respectively, and transurethral dissection and pluck in 163. 114(28.4%) patients had a bladder recurrence during follow-up. There was no difference in B-RFS between lower-end techniques by Kaplan-Meier (p = 0.94). When all factors were taken into account by adjusted Cox-regression, preceding ureteroscopy (HR 2.65, p = 0.001), lower ureteric tumour location (HR 2.16, p = 0.02), previous bladder cancer (HR 1.75, p = 0.01) and male gender (HR 1.61, p = 0.03) were associated with B-RFS. CONCLUSION: These data suggest in appropriately selected patients, lower ureteric management technique does not affect B-RFS. Along with lower ureteric tumour location, male gender and previous bladder cancer, preceding ureteroscopy was associated with a higher recurrence rate following NU, and the indication for this should be carefully considered.

Comparative analyses of dynamic transcriptome profiles highlight key response genes and dominant isoforms for muscle development and growth in chicken.

BACKGROUND: Modern breeding strategies have resulted in significant differences in muscle mass between indigenous chicken and specialized broiler. However, the molecular regulatory mechanisms that underlie these differences remain elusive. The aim of this study was to identify key genes and regulatory mechanisms underlying differences in breast muscle development between indigenous chicken and specialized broiler. RESULTS: Two time-series RNA-sequencing profiles of breast muscles were generated from commercial Arbor Acres (AA) broiler (fast-growing) and Chinese indigenous Lushi blue-shelled-egg (LS) chicken (slow-growing) at embryonic days 10, 14, and 18, and post-hatching day 1 and weeks 1, 3, and 5. Principal component analysis of the transcriptome profiles showed that the top four principal components accounted for more than 80% of the total variance in each breed. The developmental axes between the AA and LS chicken overlapped at the embryonic stages but gradually separated at the adult stages. Integrative investigation of differentially-expressed transcripts contained in the top four principal components identified 44 genes that formed a molecular network associated with differences in breast muscle mass between the two breeds. In addition, alternative splicing analysis revealed that genes with multiple isoforms always had one dominant transcript that exhibited a significantly higher expression level than the others. Among the 44 genes, the TNFRSF6B gene, a mediator of signal transduction pathways and cell proliferation, harbored two alternative splicing isoforms, TNFRSF6B-X1 and TNFRSF6B-X2. TNFRSF6B-X1 was the dominant isoform in both breeds before the age of one week. A switching event of the dominant isoform occurred at one week of age, resulting in TNFRSF6B-X2 being the dominant isoform in AA broiler, whereas TNFRSF6B-X1 remained the dominant isoform in LS chicken. Gain-of-function assays demonstrated that both isoforms promoted the proliferation of chicken primary myoblasts, but only TNFRSF6B-X2 augmented the differentiation and intracellular protein content of chicken primary myoblasts. CONCLUSIONS: For the first time, we identified several key genes and dominant isoforms that may be responsible for differences in muscle mass between slow-growing indigenous chicken and fast-growing commercial broiler. These findings provide new insights into the regulatory mechanisms underlying breast muscle development in chicken.

Genetic markers associated with bone composition in Rhode Island Red laying hens.

BACKGROUND: Bone damage has welfare and economic impacts on modern commercial poultry and is known as one of the major challenges in the poultry industry. Bone damage is particularly common in laying hens and is probably due to the physiological link between bone and the egg laying process. Previous studies identified and validated quantitative trait loci (QTL) for bone strength in White Leghorn laying hens based on several measurements, including bone composition measurements on the cortex and medulla of the tibia bone. In a previous pedigree-based analysis, bone composition measurements showed heritabilities ranging from 0.18 to 0.41 and moderate to strong genetic correlations with tibia strength and density. Bone composition was measured using infrared spectroscopy and thermogravimetry. The aim of this study was to combine these bone composition measurements with genotyping data via a genome-wide association study (GWAS) to investigate genetic markers that contribute to genetic variance in bone composition in Rhode Island Red laying hens. In addition, we investigated the genetic correlations between bone composition and bone strength. RESULTS: We found novel genetic markers that are significantly associated with cortical lipid, cortical mineral scattering, medullary organic matter, and medullary mineralization. Composition of the bone organic matter showed more significant associations than bone mineral composition. We also found interesting overlaps between the GWAS results for tibia composition traits, particularly for cortical lipid and tibia strength. Bone composition measurements by infrared spectroscopy showed more significant associations than thermogravimetry measurements. Based on the results of infrared spectroscopy, cortical lipid showed the highest genetic correlations with tibia density, which was negative (- 0.20 ± 0.04), followed by cortical CO3/PO4 (0.18 ± 0.04). Based on the results of thermogravimetry, medullary organic matter% and mineral% showed the highest genetic correlations with tibia density (- 0.25 ± 0.04 and 0.25 ± 0.04, respectively). CONCLUSIONS: This study detected novel genetic associations for bone composition traits, particularly those involving organic matter, that could be used as a basis for further molecular genetic investigations. Tibia cortical lipids displayed the strongest genetic associations of all the composition measurements, including a significantly high genetic correlation with tibia density and strength. Our results also highlighted that cortical lipid may be a key measurement for further avian bone studies.