Project: Mammographic Breast Cancer Detection with Bilateral Asymmetry Fusion and Conformal Uncertainty Quantification Module: ACM 40960 · Project 8 — Disease Modelling · University College Dublin

Literature Review [Current Milestone] Related work is selected strictly against the project's two core considerations — bilateral asymmetry fusion and conformal uncertainty quantification — as well as the backbone, clinical baselines, and datasets they depend on.

Huang 2017 — DenseNet (backbone architecture) McKinney 2020 — DeepMind/Nature (clinical performance baseline) Wu 2019 — NYU (reproducible multi-view template) Lee 2017 — CBIS-DDSM (primary dataset) Wu 2020 — Dual-View (closest architectural antecedent) Nguyen 2019 — Bilateral asymmetry (direct precursor, δ = |f_L − f_R|) Yang 2021 — Counterfactual bilateral (differentiation point) Angelopoulos 2021 — Conformal prediction tutorial (coverage guarantee) Romano 2020 — RAPS (size-regularised prediction sets, implemented variant)

Written in a thematic, concept-driven style modelled on an Irish PhD related-work chapter: papers are woven in subtly as numbered citations supporting claims, rather than discussed one by one. Sections build an argument toward the gap the project fills — the union of bilateral asymmetry fusion with conformal uncertainty, which the literature motivates but nowhere assembles.